According to Charlie Gibbs <cgibbs@kltpzyxm.invalid>:

As you pointed out, mainframes are block-oriented, rather than character >oriented. To me, this - not size - is the distinguishing characteristic >between mainframes and minis. By this logic, a mainframe the size of a >PDP-11 is still a mainframe, while a mini the size of a mainframe (e.g.
a big PDP-10) is still a mini.

I agree. I've often mentioned the 360/30 whose CPU was considerably slower
than a PDP-8 but made it up with industrial strength peripherals. As time
went on that distinction became fuzzier. The KL10 had a PDP-11 front end
that offloaded most (all?) of the low speed I/O, and DEC had the MASSBUS
for disks and tapes which definitely did block transfers.

These days, the disk controller chip in your laptop is vastly more capable
than a 1960s channel so these days the distinctive thing about mainframes
is their extensive reliability features. IBM mainframes have hot spare
CPUs that they can swap in without the program noticing, and hardware
that allows major upgrades without a reboot.

--
Regards,
John Levine, johnl@taugh.com, Primary Perpetrator of "The Internet for Dummies",
Please consider the environment before reading this e-mail. https://jl.ly

--- PyGate Linux v1.0
* Origin: Dragon's Lair, PyGate NNTP<>Fido Gate (3:633/10)

John Levine <johnl@taugh.com> writes:

According to Charlie Gibbs <cgibbs@kltpzyxm.invalid>:

As you pointed out, mainframes are block-oriented, rather than character
oriented. To me, this - not size - is the distinguishing characteristic
between mainframes and minis. By this logic, a mainframe the size of a
PDP-11 is still a mainframe, while a mini the size of a mainframe (e.g.
a big PDP-10) is still a mini.

I agree. I've often mentioned the 360/30 whose CPU was considerably slower than a PDP-8 but made it up with industrial strength peripherals. As time went on that distinction became fuzzier. The KL10 had a PDP-11 front end that offloaded most (all?) of the low speed I/O, and DEC had the MASSBUS
for disks and tapes which definitely did block transfers.

The IObus on the earlier models of the PDP-10 (including the PDP-6) also did block transfers.

These were mainframe systems, in 1960s terms.

These days, the disk controller chip in your laptop is vastly more capable than a 1960s channel so these days the distinctive thing about mainframes
is their extensive reliability features. IBM mainframes have hot spare
CPUs that they can swap in without the program noticing, and hardware
that allows major upgrades without a reboot.

And enough cycles that those disk controller chips which only speak FBA still deliver CKD blocks to the OS.

--
Rich Alderson news@alderson.users.panix.com
Audendum est, et veritas investiganda; quam etiamsi non assequamur,
omnino tamen proprius, quam nunc sumus, ad eam perveniemus.
--Galen

--- PyGate Linux v1.0
* Origin: Dragon's Lair, PyGate NNTP<>Fido Gate (3:633/10)

It appears that Rich Alderson <news@alderson.users.panix.com> said:

The IObus on the earlier models of the PDP-10 (including the PDP-6) also did >block transfers.

I realize you were there and I wasn't but I'm looking at the manual for the PDP-6
136 data control and I don't see it. The sample programs use BLKI or BLKO in in interrupt location to do pseudo-DMA.

The PDP-10 at Yale had RP02s and I can believe it did DMA.

These were mainframe systems, in 1960s terms.

Sort of. There was nothing like a 360's channel program.

--
Regards,
John Levine, johnl@taugh.com, Primary Perpetrator of "The Internet for Dummies",
Please consider the environment before reading this e-mail. https://jl.ly

--- PyGate Linux v1.0
* Origin: Dragon's Lair, PyGate NNTP<>Fido Gate (3:633/10)